SCALABLE COMPUTING Practice and Experience Special Issue: Simulation in Emergent Computational Systems

In order to provide credible and valid simulation results it is important to built simulation models that accurately represent the environments were ad hoc networks will be deployed. Recent research results have shown that there is a disparity of 30% between protocol performance in real test beds and the one in simulation environments. In this paper we summarize the recent trends on the simulation models for ad hoc networks. First, we provide a survey of the synthetic and real traffic models used in ad hoc network simulation studies. Second, we select a representative of the most used mobility synthetic model, the real pedestrian mobility model, and the real vehicular model (for mixed traffic). We show that the real pedestrian and real vehicular model share common mobility characteristics: a) The transition matrix on both models illustrate that wireless nodes do not move from one location to another at random, but they are rather based on activities (work, shopping, college, gym); b) The dynamic membership property illustrates that nodes join and leave the simulation based on some variable distribution or patterns. Lastly, via simulations we show that when using realistic simulation models the simulation protocol performance closer reflects with the real test bed protocol performance.